X-Git-Url: https://git.armaanb.net/?p=lightcards.git;a=blobdiff_plain;f=lightcards%2Fparse.py;h=3a1306bfae98840ba312fc58deff160d667ceeb8;hp=65cad627d4cd25e38dce77973fb9b25ae958a6dd;hb=8a9fa6416484726f2c7e8386a53fbdb9e5130ed0;hpb=852be3a599b3686e20b2f3bfe10291380fcc5ff7 diff --git a/lightcards/parse.py b/lightcards/parse.py old mode 100755 new mode 100644 index 65cad62..3a1306b --- a/lightcards/parse.py +++ b/lightcards/parse.py @@ -1,4 +1,3 @@ -#!/usr/bin/env python # Parse markdown table into tuple of lists # Armaan Bhojwani 2021 @@ -11,30 +10,35 @@ from .deck import Card def md2html(file): """Use the markdown module to convert input to HTML""" - with open(file, "r", encoding="utf-8") as input_file: - return markdown.markdown(input_file.read(), extensions=['tables']) + try: + return markdown.markdown(open(file, "r").read(), extensions=["tables"]) + except FileNotFoundError: + raise Exception( + f'lightcards: "{file}": No such file or directory' + ) from None def parse_html(html): """Use BeautifulSoup to parse the HTML""" + def clean_text(inp): return inp.get_text().rstrip() - def clean_list(inp): - for z in inp: - if not len(z) == 2: - inp.remove(z) - return inp - - soup = BeautifulSoup(html, 'html.parser') + soup = BeautifulSoup(html, "html.parser").find("table") outp = [] - for x in soup.find_all("tr"): - outp.append(Card([clean_text(y) for y in x.find_all("td")])) + try: + for x in soup.find_all("tr"): + outp.append(Card(tuple([clean_text(y) for y in x.find_all("td")]))) + except AttributeError: + raise Exception("lightcards: No table found") from None + + ths = soup.find_all("th") + if len(ths) != 2: + raise Exception("lightcards: Headings malformed") # Return a tuple of nested lists - return ([clean_text(x) for x in soup.find_all("th")], - clean_list(outp)) + return ([clean_text(x) for x in ths], outp[1:]) def main(file):